Methods › Audio › Text-to-Speech Models › Deep Voice 3
Deep Voice 3
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Deep Voice 3 (DV3) is a fully-convolutional attention-based neural text-to-speech system. The Deep Voice 3 architecture consists of three components:
-
Encoder: A fully-convolutional encoder, which converts textual features to an internal learned representation.
-
Decoder: A fully-convolutional causal decoder, which decodes the learned representation with a multi-hop convolutional attention mechanism into a low-dimensional audio representation (mel-scale spectrograms) in an autoregressive manner.
-
Converter: A fully-convolutional post-processing network, which predicts final vocoder parameters (depending on the vocoder choice) from the decoder hidden states. Unlike the decoder, the converter is non-causal and can thus depend on future context information.
The overall objective function to be optimized is a linear combination of the losses from the decoder and the converter. The authors separate decoder and converter and apply multi-task training, because it makes attention learning easier in practice. To be specific, the loss for mel-spectrogram prediction guides training of the attention mechanism, because the attention is trained with the gradients from mel-spectrogram prediction besides vocoder parameter prediction.
Papers archive 2025-07-28
3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Parallel Neural Text-to-Speech 1 Jan 2020 · 0 repositories
-
Non-Autoregressive Neural Text-to-Speech 21 May 2019 · 2 repositories · arXiv:1905.08459Syntology ran 2 of 7 samples · 5 unverified
-
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning 20 Oct 2017 · 7 repositories · arXiv:1710.07654Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Text to Speech | 3 |
| text-to-speech | 3 |
| GPU | 1 |
| Speech Synthesis | 1 |
| Text-To-Speech Synthesis | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections